import pandas as pd
import numpy as np
import missingno as msno
import matplotlib.pyplot as plt 
import seaborn as sns
import sys
import os
import statsmodels.api as sm
import math
import plotly.express as px #graphing
import plotly.graph_objects as go #graphing
from plotly.subplots import make_subplots #graphing
from datetime import datetime, timedelta

#!pip install missingno

path = "/Users/ycq/Downloads/Principal/"
df =pd.read_csv(path + "/Quant Exercise.csv")

Exploratory Data Analysis

df.head(), df.info(), df.shape

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 68 entries, 0 to 67
Columns: 551 entries, DP03_0001E to fips
dtypes: float64(300), int64(249), object(2)
memory usage: 292.8+ KB

(   DP03_0001E  DP03_0001M  DP03_0001PE  DP03_0001PM  DP03_0002E  DP03_0002M  \
 0       84387         137      84387.0          NaN     53245.0         910   
 1     1015608         631    1015608.0          NaN    660484.0        3044   
 2       54444         101      54444.0          NaN     31615.0         519   
 3      136682         202     136682.0          NaN     84153.0        1035   
 4       40064          86      40064.0          NaN     23144.0         447   
 
    DP03_0002PE  DP03_0002PM  DP03_0003E  DP03_0003M  ...  DP03_0136M  \
 0         63.1          1.1       53200         911  ...         NaN   
 1         65.0          0.3      659555        3038  ...         NaN   
 2         58.1          1.0       31593         518  ...         NaN   
 3         61.6          0.7       84051        1040  ...         NaN   
 4         57.8          1.1       23140         447  ...         NaN   
 
    DP03_0136PE  DP03_0136PM  DP03_0137E  DP03_0137M  DP03_0137PE  DP03_0137PM  \
 0          6.2          0.8         NaN         NaN         17.4          1.8   
 1          7.7          0.4         NaN         NaN         21.3          0.7   
 2          8.4          1.1         NaN         NaN         23.8          2.2   
 3          6.8          0.7         NaN         NaN         20.8          1.3   
 4          8.0          1.2         NaN         NaN         25.0          3.2   
 
            GEO_ID     county     fips  
 0  0500000US42001      Adams  42001.0  
 1  0500000US42003  Allegheny  42003.0  
 2  0500000US42005  Armstrong  42005.0  
 3  0500000US42007     Beaver  42007.0  
 4  0500000US42009    Bedford  42009.0  
 
 [5 rows x 551 columns],
 None,
 (68, 551))

df.describe(), df.columns, df.isnull().sum()

(       total_population   DP03_0001M   DP03_0001PE    labor_force  \
 count      6.700000e+01    67.000000  6.700000e+01      66.000000   
 mean       1.560604e+05   230.701493  1.560674e+05   96172.303030   
 std        2.234164e+05   201.079512  2.234279e+05  144659.556679   
 min        3.880000e+03    30.000000  3.880000e+03    1493.000000   
 25%        3.464200e+04    95.500000  3.464200e+04   19214.500000   
 50%        7.106000e+04   157.000000  7.106000e+04   39691.500000   
 75%        1.720595e+05   315.000000  1.720595e+05  102158.250000   
 max        1.272154e+06  1209.000000  1.272154e+06  783168.000000   
 
         DP03_0002M  DP03_0002PE  DP03_0002PM  civ_labor_force   DP03_0003M  \
 count    67.000000    67.000000    67.000000        67.000000    67.000000   
 mean   1008.044776    58.907463     1.094030     97881.895522  1009.134328   
 std     866.090177     6.430828     0.634102    144187.169841   865.600000   
 min     119.000000    21.500000     0.300000      1493.000000   119.000000   
 25%     439.500000    56.050000     0.700000     19409.500000   438.500000   
 50%     767.000000    59.400000     1.000000     39824.000000   766.000000   
 75%    1362.000000    62.550000     1.300000    104556.500000  1364.500000   
 max    5667.000000    68.300000     4.400000    782637.000000  5648.000000   
 
        DP03_0003PE  ...  DP03_0133PM  DP03_0134PE  DP03_0134PM  DP03_0135PE  \
 count    67.000000  ...    67.000000    67.000000    67.000000    67.000000   
 mean     58.832836  ...     1.001493    11.685075     1.235821     7.947761   
 std       6.409756  ...     0.544808     3.598706     0.774343     2.047420   
 min      21.500000  ...     0.300000     5.300000     0.300000     4.300000   
 25%      56.050000  ...     0.600000     9.300000     0.800000     6.850000   
 50%      59.200000  ...     0.900000    11.200000     1.100000     7.900000   
 75%      62.550000  ...     1.200000    13.100000     1.500000     8.850000   
 max      68.200000  ...     3.000000    22.900000     4.400000    18.100000   
 
        DP03_0135PM  DP03_0136PE  DP03_0136PM  DP03_0137PE  DP03_0137PM  \
 count    67.000000    67.000000    67.000000    67.000000    67.000000   
 mean      1.465672     8.834328     1.258209    23.802985     2.444776   
 std       0.738662     2.852939     0.677372     4.962312     1.273302   
 min       0.400000     3.700000     0.400000    15.300000     0.700000   
 25%       0.850000     6.800000     0.800000    20.650000     1.500000   
 50%       1.400000     8.400000     1.200000    23.300000     2.200000   
 75%       1.700000    10.050000     1.500000    25.850000     2.900000   
 max       3.800000    20.400000     4.200000    44.300000     7.000000   
 
                fips  
 count     67.000000  
 mean   42067.000000  
 std       38.970074  
 min    42001.000000  
 25%    42034.000000  
 50%    42067.000000  
 75%    42100.000000  
 max    42133.000000  
 
 [8 rows x 458 columns],
 Index(['total_population', 'DP03_0001M', 'DP03_0001PE', 'labor_force',
        'DP03_0002M', 'DP03_0002PE', 'DP03_0002PM', 'civ_labor_force',
        'DP03_0003M', 'DP03_0003PE',
        ...
        'DP03_0134PM', 'DP03_0135PE', 'DP03_0135PM', 'DP03_0136PE',
        'DP03_0136PM', 'DP03_0137PE', 'DP03_0137PM', 'GEO_ID', 'county',
        'fips'],
       dtype='object', length=460),
 total_population    0
 DP03_0001M          0
 DP03_0001PE         0
 labor_force         1
 DP03_0002M          0
                    ..
 DP03_0137PE         0
 DP03_0137PM         0
 GEO_ID              0
 county              0
 fips                0
 Length: 460, dtype: int64)

df.dtypes

total_population      int64
DP03_0001M            int64
DP03_0001PE         float64
labor_force         float64
DP03_0002M            int64
                     ...   
DP03_0137PE         float64
DP03_0137PM         float64
GEO_ID               object
county               object
fips                float64
Length: 460, dtype: object

Sourced from credit bureau data

The column header names do not provide a good description of the data. I located the columns that I wanted to use and created a dictionary with the key value pairs for the column header names which can be seen below.

I also added a FIPS county code column to the dataset for each county in Pennsylvania. FIPS is a five-digit Federal Information Processing Standards code which uniquely identifies counties in the United States. We can use FIPS along with geojson to create Choropleth Maps.

# Dictionary of all renamed columns
# All of the renamed columns are ESTIMATES from the U.S. Census Bureau
# Columns not renamed include: Percent (PE), Margin of Error (M), Percent Margin of Error (PM)

dict = {# Employment Status
        # Population 16 years and over
        "DP03_0001E" : "total_population", # Total Population elgible for work
        "DP03_0002E" : "labor_force",
        "DP03_0003E" : "civ_labor_force",
        "DP03_0004E" : "total_employed",
        "DP03_0005E" : "total_unemployed",
        "DP03_0006E" : "armed_forces",
        "DP03_0007E" : "not_in_labor_force",
    

        # Females 16 years and over
        "DP03_0010E" : "total_population_female", # Total Population elgible for work
        "DP03_0011E" : "labor_force_female",
        "DP03_0012E" : "civ_labor_force_female",
        "DP03_0013E" : "civ_labor_force_female_employed",
    

        # Households with children
        "DP03_0014E" : "household_children_under_6", # Own children of the householder under 6 years
        # All parents in family in labor force
        "DP03_0015E" : "parents_work_children_under_6", # Own children of the householder under 6 years
        "DP03_0016E" : "household_children_6to17", # Own children of the householder 6 to 17 years
        # All parents in family in labor force
        "DP03_0017E" : "parents_work_children_6to17", # Own children of the householder 6 to 17 years
    

        # Commuting to work
        "DP03_0018E" : "total_workers_commute",
        "DP03_0019E" : "solo_vehicle_commute", # Car, truck, or van -- drove alone
        "DP03_0020E" : "carpool_commute", # Car, truck, or van -- carpooled
        "DP03_0021E" : "public_transportation_commute", # Public transportation (excluding taxicab)
        "DP03_0022E" : "walked_commute",
        "DP03_0023E" : "other_means_commute",
        "DP03_0024E" : "worked_from_home",
        "DP03_0025E" : "mean_commute_time_minutes",
    

        # Occupation
        "DP03_0027E" : "manage_business_sci_art", # Management, business, science, and arts occupations
        "DP03_0028E" : "service_occupations",
        "DP03_0029E" : "sales_and_office_occupations",
        # Natural resources, construction, and maintenance occupations
        "DP03_0030E" : "nr_construction_and_maintenance",
        # Production, transportation, and material moving occupations
        "DP03_0031E" : "production_transportation_mm",
    

        # Industry
        "DP03_0033E" : "ag_forest_fish_hunt_mine", # Agriculture, forestry, fishing and hunting, and mining
        "DP03_0034E" : "construction",
        "DP03_0035E" : "manufacturing",
        "DP03_0036E" : "wholesale_trade",
        "DP03_0037E" : "retail_trade",
        "DP03_0038E" : "transportation_warehousing_utilities",
        "DP03_0039E" : "information",
        "DP03_0040E" : "firerl", # Finance, insurance, real estate, rental and leasing
        # Professional, scientific, and management, and administrative and waste management services
        "DP03_0041E" : "psmawms",
        # Educational services, and health care and social assistance
        "DP03_0042E" : "education_health_care_social",
        # Arts, entertainment, and recreation, and accommodation and food services
        "DP03_0043E" : "art_entertainment_accommodation",
        "DP03_0044E" : "other_services", # Other services, except public administration
        "DP03_0045E" : "public_administration",
    

        # Class of worker
        "DP03_0047E" : "private_wage_and_salary_worker",
        "DP03_0048E" : "government_worker",
        "DP03_0049E" : "self_employed_worker", # Self-employed in own not incorporated business workers
        "DP03_0050E" : "unpaid_family_worker",
    

        # Income and benefits (in 2020 inflation-adjusted dollars)
        # Total households
        "DP03_0051E" : "total_households",
        "DP03_0052E" : "household_less_than_10k",
        "DP03_0053E" : "household_10k_to_15k", # $10,000 to $14,999
        "DP03_0054E" : "household_15k_to_25k", # $15,000 to $24,999
        "DP03_0055E" : "household_25k_to_35k", # $25,000 to $34,999
        "DP03_0056E" : "household_35k_to_50k", # $35,000 to $49,999
        "DP03_0057E" : "household_50k_to_75k", # $50,000 to $74,999
        "DP03_0058E" : "household_75k_to_100k", # $75,000 to $99,999
        "DP03_0059E" : "household_100k_to_150k", # $100,000 to $149,999
        "DP03_0060E" : "household_150k_to_200k", # $150,000 to $199,999
        'DP03_0061E' : "household_200k_plus", # $200,000 or more
        "DP03_0062E" : "household_median_income", # dollars
        "DP03_0063E" : "household_mean_income", # dollars

    
        # Families
        "DP03_0075E" : "total_families",
        "DP03_0076E" : "family_less_than_10k",
        "DP03_0077E" : "family_10k_to_15k", # $10,000 to $14,999
        "DP03_0078E" : "family_15k_to_25k", # $15,000 to $24,999
        "DP03_0079E" : "family_25k_to_35k", # $25,000 to $34,999
        "DP03_0080E" : "family_35k_to_50k", # $35,000 to $49,999
        "DP03_0081E" : "family_50k_to_75k", # $50,000 to $74,999
        "DP03_0082E" : "family_75k_to_100k", # $75,000 to $99,999
        "DP03_0083E" : "family_100k_to_150k", # $100,000 to $149,999
        "DP03_0084E" : "family_150k_to_200k", # $150,000 to $199,999
        "DP03_0085E" : "family_200k_plus", # $200,000 or more
        "DP03_0086E" : "family_median_income", # dollars
        "DP03_0087E" : "family_mean_income", # dollars
        "DP03_0088E" : "per_capita_income",

    
        # Nonfamily Households
        "DP03_0089E" : "total_nonfamily_households",
        "DP03_0090E" : "nonfamily_median_income", # dollars
        "DP03_0091E" : "nonfamily_mean_income", # dollars
    
    
        # Median Earnings
        "DP03_0092E" : "median_earnings_for_workers", # dollars
        "DP03_0093E" : "median_earnings_male_fulltime", # dollars
        "DP03_0094E" : "median_earnings_female_fulltime", # dollars

    
        # Health Insurance Coverage
        "DP03_0095E" : "total_civ_population", # Total Civilian Noninstitutionalized Population
        "DP03_0096E" : "civ_health_insurance_coverage", # Population
        "DP03_0097E" : "civ_private_health_insurance", # Population
        "DP03_0098E" : "civ_public_health_insurance", # Population
        "DP03_0099E" : "civ_no_health_insurance"} # Population

df.rename(columns = dict, inplace = True)

df = df.dropna(axis=1, how="all")

df.head()

	total_population	DP03_0001M	DP03_0001PE	labor_force	DP03_0002M	DP03_0002PE	DP03_0002PM	civ_labor_force	DP03_0003M	DP03_0003PE	...	DP03_0134PM	DP03_0135PE	DP03_0135PM	DP03_0136PE	DP03_0136PM	DP03_0137PE	DP03_0137PM	GEO_ID	county	fips
0	84387	137	84387.0	53245.0	910	63.1	1.1	53200	911	63.0	...	0.8	5.7	0.9	6.2	0.8	17.4	1.8	0500000US42001	Adams	42001.0
1	1015608	631	1015608.0	660484.0	3044	65.0	0.3	659555	3038	64.9	...	0.3	8.5	0.6	7.7	0.4	21.3	0.7	0500000US42003	Allegheny	42003.0
2	54444	101	54444.0	31615.0	519	58.1	1.0	31593	518	58.0	...	1.0	9.2	1.6	8.4	1.1	23.8	2.2	0500000US42005	Armstrong	42005.0
3	136682	202	136682.0	84153.0	1035	61.6	0.7	84051	1040	61.5	...	0.7	7.2	0.9	6.8	0.7	20.8	1.3	0500000US42007	Beaver	42007.0
4	40064	86	40064.0	23144.0	447	57.8	1.1	23140	447	57.8	...	1.6	9.4	1.6	8.0	1.2	25.0	3.2	0500000US42009	Bedford	42009.0

5 rows × 460 columns

df.tail(), df.county.nunique

(    total_population  DP03_0001M  DP03_0001PE  labor_force  DP03_0002M  \
 63             43821         104      43821.0      22241.0         767   
 64            294500         356     294500.0     179495.0        1512   
 65             22487          77      22487.0      13226.0         319   
 66            360718         453     360718.0     237353.0        1629   
 67          10456049        2462   10456049.0    6566126.0       11721   
 
     DP03_0002PE  DP03_0002PM  civ_labor_force  DP03_0003M  DP03_0003PE  ...  \
 63         50.8          1.7            22229         766         50.7  ...   
 64         60.9          0.5           179459        1511         60.9  ...   
 65         58.8          1.4            13217         318         58.8  ...   
 66         65.8          0.5           237053        1634         65.7  ...   
 67         62.8          0.1          6558087       11636         62.7  ...   
 
     DP03_0134PM  DP03_0135PE  DP03_0135PM  DP03_0136PE  DP03_0136PM  \
 63          1.7          6.4          1.5          7.4          1.6   
 64          0.5          7.2          0.7          6.4          0.5   
 65          1.4          8.1          1.7          7.8          1.3   
 66          0.5          6.8          0.8          6.3          0.5   
 67          0.1          8.2          0.2          9.0          0.2   
 
     DP03_0137PE  DP03_0137PM          GEO_ID        county     fips  
 63         24.8          2.8  0500000US42127         Wayne  42127.0  
 64         21.4          1.2  0500000US42129  Westmoreland  42129.0  
 65         21.9          2.7  0500000US42131       Wyoming  42131.0  
 66         20.0          1.4  0500000US42133          York  42133.0  
 67         23.3          0.3     0400000US42  Pennsylvania      NaN  
 
 [5 rows x 460 columns],
 <bound method IndexOpsMixin.nunique of 0            Adams
 1        Allegheny
 2        Armstrong
 3           Beaver
 4          Bedford
           ...     
 63           Wayne
 64    Westmoreland
 65         Wyoming
 66            York
 67    Pennsylvania
 Name: county, Length: 68, dtype: object>)

df0 = df[df["county"] == "Pennsylvania"]
df = df[df["county"] != "Pennsylvania"]

print(df.county.unique())

['Adams' 'Allegheny' 'Armstrong' 'Beaver' 'Bedford' 'Berks' 'Blair'
 'Bradford' 'Bucks' 'Butler' 'Cambria' 'Cameron' 'Carbon' 'Centre'
 'Chester' 'Clarion' 'Clearfield' 'Clinton' 'Columbia' 'Crawford'
 'Cumberland' 'Dauphin' 'Delaware' 'Elk' 'Erie' 'Fayette' 'Forest'
 'Franklin' 'Fulton' 'Greene' 'Huntingdon' 'Indiana' 'Jefferson' 'Juniata'
 'Lackawanna' 'Lancaster' 'Lawrence' 'Lebanon' 'Lehigh' 'Luzerne'
 'Lycoming' 'McKean' 'Mercer' 'Mifflin' 'Monroe' 'Montgomery' 'Montour'
 'Northampton' 'Northumberland' 'Perry' 'Philadelphia' 'Pike' 'Potter'
 'Schuylkill' 'Snyder' 'Somerset' 'Sullivan' 'Susquehanna' 'Tioga' 'Union'
 'Venango' 'Warren' 'Washington' 'Wayne' 'Westmoreland' 'Wyoming' 'York']

Above is most of the data cleaning process, with labeling, missing value treatment, data formatting.

Data Visulization - a brief overview of the data

plt.rcParams["figure.figsize"] = (12, 8)

# Importing county data for Plotly Choropleth Maps
from urllib.request import urlopen
import json
with urlopen("https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json") as response:
    counties = json.load(response)

#Pennsylvania Household Income and Benefits 

plt.style.use('seaborn-dark')
plot = df0[["county", "household_less_than_10k", "household_10k_to_15k", "household_15k_to_25k",
                      "household_25k_to_35k", "household_35k_to_50k", "household_50k_to_75k",
                      "household_75k_to_100k", "household_100k_to_150k", "household_150k_to_200k",
                      "household_200k_plus"]].plot(x = "county", kind = "bar", cmap = "Spectral")

plt.grid(axis = 'y', alpha = 0.3)
plot.set_xticklabels(plot.get_xticklabels(), rotation = 360, fontsize = 20)
plt.title("Distribution of Pennsylvania Total Household Income", fontsize = 25)
plt.legend(bbox_to_anchor = (1.02, 1), loc = 2, borderaxespad = 0, fontsize = 15)

/var/folders/2r/y399hm9d0hv3ysx7v92kl9l80000gn/T/ipykernel_57748/2960315682.py:3: MatplotlibDeprecationWarning: The seaborn styles shipped by Matplotlib are deprecated since 3.6, as they no longer correspond to the styles shipped by seaborn. However, they will remain available as 'seaborn-v0_8-<style>'. Alternatively, directly use the seaborn API instead.
  plt.style.use('seaborn-dark')

<matplotlib.legend.Legend at 0x7fb2c1153a00>

# Percentage of Households with less than $50,000 income 

df["household_less_than_50k"] = df["household_less_than_10k"] + df["household_10k_to_15k"] + df["household_15k_to_25k"] + df["household_25k_to_35k"] + df["household_35k_to_50k"]

df["household_less_than_50k_percentage"] = (df["household_less_than_50k"]/df["total_households"]) * 100

fig = px.choropleth_mapbox(df, geojson = counties, locations = "fips", 
                           color = "household_less_than_50k_percentage",
                           color_continuous_scale = "Reds",
                           mapbox_style = "carto-darkmatter",
                           zoom = 6.25, center = {"lat": 41, "lon": -77.65},
                           hover_name = "county",
                           labels = {"household_less_than_50k_percentage": "% Household < $50,000 💰"}
                          )
                                     
fig.update_layout(margin = {"r": 0,"t": 0,"l": 0,"b": 0})
fig.update_layout(template = "plotly_white")
fig.show()

# Percentage of Households with more than $100,000 income 

df["household_100k_plus"] = df["household_100k_to_150k"] + df["household_150k_to_200k"] + df["household_200k_plus"]

df["household_100k_plus_percentage"] = (df["household_100k_plus"]/df["total_households"]) * 100

fig = px.choropleth_mapbox(df, geojson = counties, locations = "fips", 
                           color = "household_100k_plus_percentage",
                           color_continuous_scale = "Greens",
                           mapbox_style = "carto-darkmatter",
                           zoom = 6.25, center = {"lat": 41, "lon": -78},
                           hover_name = "county",
                           labels = {"household_100k_plus_percentage": "% Household > $100,000 💰"}
                          )
                                     
fig.update_layout(margin = {"r": 0,"t": 0,"l": 0,"b": 0})
fig.update_layout(template = "plotly_white")
fig.show()

Pennsylvania Employment Analysis

# Total Employment Rate

df["employment_rate"] = (df["total_employed"]/df["labor_force"]) * 100

fig = px.choropleth_mapbox(df, geojson = counties, locations = "fips", 
                           color = "employment_rate",
                           color_continuous_scale = "RdBu_r",
                           range_color = (91.5, 97.5),
                           mapbox_style = "carto-darkmatter",
                           zoom = 6.25, center = {"lat": 41, "lon": -77.65},
                           hover_name = "county",
                           hover_data = ["total_employed", "total_unemployed"],
                           labels = {"employment_rate": "Employment Rate",
                                     "total_employed": "Total Employed",
                                     "total_unemployed": "Total Unemployed"}
                          )

fig.update_layout(margin = {"r": 0,"t": 0,"l": 0,"b": 0})
fig.update_layout(template = "plotly_dark")
fig.show()

# Employment Rate Percentage by County¶


df["labor_force_male"] = df["labor_force"] - df["labor_force_female"]
df["total_male_employed"] = df["total_employed"] - df["civ_labor_force_female_employed"]
df["employment_rate_male"] = (df["total_male_employed"]/df["labor_force_male"]) * 100
df["employment_rate_female"] = (df["civ_labor_force_female_employed"]/df["civ_labor_force_female"]) * 100


plt.style.use("Solarize_Light2")

x1 = df.employment_rate_male
x2 = df.employment_rate_female
x3 = df.employment_rate
y = df.county

plt.figure(figsize = (6, 14), dpi = 80)
plt.scatter(x1, y, color = "#0000FF", edgecolors = "#000000", s = 50, alpha = 0.75, label = "Male Employment Rate %")
plt.scatter(x2, y, color = "#FF00FF", edgecolors = "#000000", s = 50, alpha = 0.75, label = "Female Employment Rate %")
plt.plot(x3, y, color = "#000000", alpha = 0.5, linestyle = "dashed", label = "Total Employment Rate %")
plt.grid(color = "#d3d3d3", linestyle = '-', linewidth = 0.75)
plt.title("Employment Rate % by County")
plt.xlabel("Employment Rate Percentage")
plt.ylabel("")
plt.legend(loc = 2)
plt.show()

Pennsylvania Median Earnings by County

#Pennsylvania Median Earnings by County 


plt.style.use("Solarize_Light2")

x1 = df.median_earnings_for_workers
x2 = df.median_earnings_male_fulltime
x3 = df.median_earnings_female_fulltime
y = df.county

plt.figure(figsize = (8, 14), dpi = 80)
plt.scatter(x1, y, color = "#000000", alpha = 1, s = 12, label = "All Workers")
plt.plot(x1, y, color = "#000000", alpha = 0.75)
plt.scatter(x2, y, color = "#0000FF", edgecolors = "#000000", label = "Male Full Time")
plt.plot(x2, y, color = "#0000FF", alpha = 0.75, linestyle = "--")
plt.scatter(x3, y, color = "#FF00FF", edgecolors = "#000000", label = "Female Full Time")
plt.plot(x3, y, color = "#FF00FF", alpha = 0.75, linestyle = "--")
plt.grid(color = "#d3d3d3", linestyle = '-', linewidth = 2)
plt.title("Pennsylvania Median Earnings by County")
plt.xlabel("Median Earnings (dollars)")
plt.ylabel("")
plt.legend(loc = 1)
plt.show()

#Pennsylvania Per Capita Income by County


plt.style.use("seaborn-dark")

x = df.per_capita_income
y = df.county

plt.figure(figsize = (8, 14), dpi = 80)
plt.scatter(x, y, color = "#00DB16", alpha = 1, s = 100, edgecolors = "#d3d3d3", label = "Per Capita Income (USD)")
plt.plot(x, y, color = "#00DB16", linestyle = "dotted")
plt.grid(color = "#d3d3d3", linestyle = '-', linewidth = 0.25)
plt.title("Pennsylvania Per Capita Income by County")
plt.xlabel("Per Capita Income (dollars)")
plt.ylabel("")
plt.legend(loc = 1)
plt.show()

/var/folders/2r/y399hm9d0hv3ysx7v92kl9l80000gn/T/ipykernel_57748/3704097254.py:4: MatplotlibDeprecationWarning:

The seaborn styles shipped by Matplotlib are deprecated since 3.6, as they no longer correspond to the styles shipped by seaborn. However, they will remain available as 'seaborn-v0_8-<style>'. Alternatively, directly use the seaborn API instead.

How People in Pennsylvania Commute to Work

# Percentage Worked From Home 


df["worked_from_home_percentage"] = (df["worked_from_home"]/df["total_workers_commute"]) * 100

fig = px.choropleth_mapbox(df, geojson = counties, locations = "fips", 
                           color = "worked_from_home_percentage",
                           color_continuous_scale = "Viridis",
                           mapbox_style = "carto-darkmatter",
                           zoom = 6.25, center = {"lat": 41, "lon": -77.65},
                           hover_name = "county",
                           labels = {"worked_from_home_percentage": "% Working From Home"}
                          )

fig.update_layout(margin = {"r": 0,"t": 0,"l": 0,"b": 0})
fig.update_layout(template = "plotly_dark")
fig.show()

Pennsylvania Health Insurance Coverage Analysis

#civ_health_insurance_coverage_percentage

df["civ_health_insurance_coverage_percentage"] = (df["civ_health_insurance_coverage"]/df["total_civ_population"]) * 100

fig = px.choropleth_mapbox(df, geojson = counties, locations = "fips", 
                           color = "civ_health_insurance_coverage_percentage",
                           color_continuous_scale = "Picnic",
                           mapbox_style = "carto-darkmatter",
                           zoom = 6.25, center = {"lat": 41, "lon": -77.65},
                           hover_name = "county",
                           labels = {"civ_health_insurance_coverage_percentage": "Percentage w/ Health Insurance 🏥"}
                          )
                                     
fig.update_layout(margin = {"r": 0,"t": 0,"l": 0,"b": 0})
fig.update_layout(template = "plotly_dark")
fig.show()

#!pip install geopandas==0.8.1
#!pip install pyshp==1.2.10
#!pip install shapely==1.6.3

#import plotly.figure_factory as ff
#fig = ff.create_choropleth(fips=df.fips, 
#                           scope=['PA'],
#                          values=df.total_population, 
#                           title='PA total population by County', 
#                           legend_title='')
#fig.layout.template = None
#fig.show()

#import plotly.figure_factory as ff

#values = range(len(df.fips))

#fig = ff.create_choropleth(fips=df.fips, values=values)
#fig.layout.template = None
#fig.show()